NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding

ArXi:2605.10065v1 Announce Type: cross Controlling Large Language Models (LLMs) to prevent the generation of undesirable content, such as profanity and personally identifiable information (PII), has become increasingly critical. While earlier approaches relied on post-processing or resampling, recent research has shifted towards constrained decoding methods that control outputs during generation to mitigate high computational costs and quality degradation.